MI

Mistral Small 3.2 24B Instruct 2506

MistralGGUF by eaddarioUpdated 2025-07-19
Download on Hugging Face
Parameters23.6B
Context128K
Layers40
Architecturellama
Smallest quant9.2 GB
Quick answer

Mistral Small 3.2 24B Instruct 2506 needs about 14.9 GB of memory at Q4_K_M (a 13.1 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 13 quants, from 9.2 GB (Q3_K_S) to 47.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.

Mistral Small 3.2 24B Instruct 2506 – a 23.6B parameter instruction‑oriented model

Mistral Small 3.2 24B Instruct 2506 is a 23.6B parameter model built on the llama architecture. It improves instruction following, reduces repetition, and enhances function‑calling compared to its predecessor. The model supports a 131072 token context window and is released under Apache‑2.0.

Good at

  • Precise instruction following
  • Reduced infinite generations
  • Robust function calling

Limits

  • No vision support
  • Requires ~55 GB GPU RAM in bf16/fp16
  • Large context length may increase memory usage

Best for

  • Chat assistants
  • Tool‑integrated workflows
  • Instruction‑driven coding help

Who it’s for. Developers and researchers needing a high‑capacity instruction‑oriented model for server‑side inference. The model is suitable for applications that can accommodate the memory demands of a 24B parameter LLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S9.2 GB 11.0 GB
Too big Get file →
IQ3_S9.8 GB 11.6 GB
Too big Get file →
Q3_K_M10.4 GB 12.3 GB
Too big Get file →
IQ3_M10.8 GB 12.7 GB
Too big Get file →
Q3_K_L11.4 GB 13.2 GB
Too big Get file →
Q4_K_S11.9 GB 13.8 GB
Too big Get file →
IQ4_NL13.1 GB 14.9 GB
Too big Get file →
Q4_K_M13.1 GB 14.9 GB
Too big Get file →
Q5_K_S14.9 GB 16.8 GB
Too big Get file →
Q5_K_M16.0 GB 17.9 GB
Too big Get file →
Q6_K19.8 GB 21.6 GB
Too big Get file →
Q8_020.8 GB 22.7 GB
Too big Get file →
F1647.2 GB 49.0 GB
Too big Get file →

For 8 GB VRAM use Q3_K_S (9.19 GB file, ~11 GB memory). For 16 GB VRAM Q4_K_S (11.95 GB file, ~13.8 GB memory). For 24 GB VRAM Q5_K_M (16.04 GB file, ~17.9 GB memory). These estimates are approximate.

What GPU do you need for Mistral Small 3.2 24B Instruct 2506?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is IQ3_S (9.8 GB file, about 11.6 GB in use).
  • 16 GB VRAM: the best quant that fits is Q4_K_M (13.1 GB file, about 14.9 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (20.8 GB file, about 22.7 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (20.8 GB file, about 22.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (20.8 GB file, about 22.7 GB in use).

Which Mistral Small 3.2 24B Instruct 2506 quant should you choose?

Q4_K_M is the usual starting point for Mistral Small 3.2 24B Instruct 2506: it balances file size and quality well. Here it is a 13.1 GB file.

The Q8_0 file is 20.8 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q3_K_S at 9.2 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters23.6B
Layers40
Trained context131,072 tokens
KV cache (fp16)160 KB per token

Source

Quantized byeaddario
FamilyMistral
Licenseapache-2.0
Downloads (HF)1,038
Last updated2025-07-19

Frequently asked questions about Mistral Small 3.2 24B Instruct 2506

How much VRAM does Mistral Small 3.2 24B Instruct 2506 need?

About 14.9 GB at Q4_K_M with an 8K context window. That is the 13.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Mistral Small 3.2 24B Instruct 2506 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Mistral Small 3.2 24B Instruct 2506 GGUF?

It depends on the quant: Q3_K_S is 9.2 GB, IQ3_S is 9.8 GB, Q3_K_M is 10.4 GB, IQ3_M is 10.8 GB, Q3_K_L is 11.4 GB, Q4_K_S is 11.9 GB and 7 more.

What context length does Mistral Small 3.2 24B Instruct 2506 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.

Where can I download Mistral Small 3.2 24B Instruct 2506 GGUF?

The files are on Hugging Face in the eaddario/Mistral-Small-3.2-24B-Instruct-2506-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Mistral Small 3.2 24B Instruct 2506 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Mistral Small 3.2 24B Instruct 2506 on 8 GB VRAM?

Only with the Q3_K_S quantization, which requires about 11 GB of VRAM at 8 k context.

Does the model support vision tasks?

No, the model does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Other GGUFs of Mistral-Small-3.2-24B-Instruct-2506

Similar models

Browse all →

More from eaddario

All by eaddario →

More Mistral models

All Mistral →

Other medium models

All medium models →